1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
\name{orangeJuice}
\alias{orangeJuice}
\docType{data}
\title{Store-level Panel Data on Orange Juice Sales}
\description{
Weekly sales of refrigerated orange juice at 83 stores. Contains demographic information on those stores.
}
\usage{data(orangeJuice)}
\format{
The \code{orangeJuice} object is a list containing two data frames, \code{yx} and \code{storedemo}.
}
\details{
In the \code{yx} data frame:
\tabular{ll}{
\ldots\code{$store } \tab store number \cr
\ldots\code{$brand } \tab brand indicator \cr
\ldots\code{$week } \tab week number \cr
\ldots\code{$logmove } \tab log of the number of units sold \cr
\ldots\code{$constant } \tab a vector of 1s \cr
\ldots\code{$price# } \tab price of brand # \cr
\ldots\code{$deal } \tab in-store coupon activity \cr
\ldots\code{$feature } \tab feature advertisement \cr
\ldots\code{$profit } \tab profit
}
The price variables correspond to the following brands:
\tabular{ll}{
1 \tab Tropicana Premium 64 oz \cr
2 \tab Tropicana Premium 96 oz \cr
3 \tab Florida's Natural 64 oz \cr
4 \tab Tropicana 64 oz \cr
5 \tab Minute Maid 64 oz \cr
6 \tab Minute Maid 96 oz \cr
7 \tab Citrus Hill 64 oz \cr
8 \tab Tree Fresh 64 oz \cr
9 \tab Florida Gold 64 oz \cr
10 \tab Dominicks 64 oz \cr
11 \tab Dominicks 128 oz
}
In the \code{storedemo} data frame:
\tabular{ll}{
\ldots\code{$STORE } \tab store number \cr
\ldots\code{$AGE60 } \tab percentage of the population that is aged 60 or older \cr
\ldots\code{$EDUC } \tab percentage of the population that has a college degree \cr
\ldots\code{$ETHNIC } \tab percent of the population that is black or Hispanic \cr
\ldots\code{$INCOME } \tab median income \cr
\ldots\code{$HHLARGE } \tab percentage of households with 5 or more persons \cr
\ldots\code{$WORKWOM } \tab percentage of women with full-time jobs \cr
\ldots\code{$HVAL150 } \tab percentage of households worth more than $150,000 \cr
\ldots\code{$SSTRDIST } \tab distance to the nearest warehouse store \cr
\ldots\code{$SSTRVOL } \tab ratio of sales of this store to the nearest warehouse store \cr
\ldots\code{$CPDIST5 } \tab average distance in miles to the nearest 5 supermarkets \cr
\ldots\code{$CPWVOL5 } \tab ratio of sales of this store to the average of the nearest five stores
}
}
\source{Alan L. Montgomery (1997), "Creating Micro-Marketing Pricing Strategies Using Supermarket Scanner Data," \emph{Marketing Science} 16(4) 315--337.}
\references{Chapter 5, \emph{Bayesian Statistics and Marketing} by Rossi, Allenby, and McCulloch.}
\examples{
## load data
data(orangeJuice)
## print some quantiles of yx data
cat("Quantiles of the Variables in yx data",fill=TRUE)
mat = apply(as.matrix(orangeJuice$yx), 2, quantile)
print(mat)
## print some quantiles of storedemo data
cat("Quantiles of the Variables in storedemo data",fill=TRUE)
mat = apply(as.matrix(orangeJuice$storedemo), 2, quantile)
print(mat)
## processing for use with rhierLinearModel
if(0) {
## select brand 1 for analysis
brand1 = orangeJuice$yx[(orangeJuice$yx$brand==1),]
store = sort(unique(brand1$store))
nreg = length(store)
nvar = 14
regdata=NULL
for (reg in 1:nreg) {
y = brand1$logmove[brand1$store==store[reg]]
iota = c(rep(1,length(y)))
X = cbind(iota,log(brand1$price1[brand1$store==store[reg]]),
log(brand1$price2[brand1$store==store[reg]]),
log(brand1$price3[brand1$store==store[reg]]),
log(brand1$price4[brand1$store==store[reg]]),
log(brand1$price5[brand1$store==store[reg]]),
log(brand1$price6[brand1$store==store[reg]]),
log(brand1$price7[brand1$store==store[reg]]),
log(brand1$price8[brand1$store==store[reg]]),
log(brand1$price9[brand1$store==store[reg]]),
log(brand1$price10[brand1$store==store[reg]]),
log(brand1$price11[brand1$store==store[reg]]),
brand1$deal[brand1$store==store[reg]],
brand1$feat[brand1$store==store[reg]] )
regdata[[reg]] = list(y=y, X=X)
}
## storedemo is standardized to zero mean.
Z = as.matrix(orangeJuice$storedemo[,2:12])
dmean = apply(Z, 2, mean)
for (s in 1:nreg) {Z[s,] = Z[s,] - dmean}
iotaz = c(rep(1,nrow(Z)))
Z = cbind(iotaz, Z)
nz = ncol(Z)
Data = list(regdata=regdata, Z=Z)
Mcmc = list(R=R, keep=1)
out = rhierLinearModel(Data=Data, Mcmc=Mcmc)
summary(out$Deltadraw)
summary(out$Vbetadraw)
## plotting examples
if(0){ plot(out$betadraw) }
}
}
\keyword{datasets}
|
